A Smartphone Indoor Localization Algorithm Based on WLAN Location Fingerprinting with Feature Extraction and...

Area of Science:

• Computer Science
• Electrical Engineering
• Signal Processing

Background:

• The increasing demand for location-based services necessitates advanced indoor localization techniques.
• Existing methods often face challenges with accuracy and computational efficiency.

Purpose of the Study:

• To develop and evaluate a novel indoor localization algorithm using Received Signal Strength (RSS).
• To improve the accuracy and reduce the computational complexity of indoor positioning systems.

Main Methods:

• An improved AP selection algorithm based on signal stability.
• Kernel Principal Component Analysis (KPCA) for nonlinear feature extraction and data redundancy reduction.
• Affinity Propagation Clustering (APC) for data classification and range narrowing.
• Maximum Likelihood (ML) estimation for precise positioning.

Main Results:

• The proposed algorithm effectively removes redundant data and extracts essential features.
• Data classification using APC narrows the positioning range, enhancing efficiency.
• Experimental evaluation in a real-world environment confirms improved accuracy and computational performance.

Conclusions:

• The developed algorithm offers a significant improvement in indoor localization accuracy.
• The integration of KPCA and APC provides an effective approach for nonlinear feature extraction and data classification in RSS-based localization.
• The algorithm presents a viable solution for enhancing location-based services in indoor environments.